Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2284 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.2374. Min Range: -3.2374

Max Act: 3.2374. Min Act: -0.0000

Data Index: 233407 (The Pile)

Max Activating Token Index: 472

Text #1

Max Range: 3.2374. Min Range: -3.2374

Max Act: 3.1711. Min Act: -0.0000

Data Index: 1360611 (The Pile)

Max Activating Token Index: 280

Text #2

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.8859. Min Act: -0.0000

Data Index: 1273637 (The Pile)

Max Activating Token Index: 591

Text #3

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.7321. Min Act: -0.0000

Data Index: 1470319 (The Pile)

Max Activating Token Index: 233

Text #4

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.7852. Min Act: -0.0000

Data Index: 214578 (The Pile)

Max Activating Token Index: 347

Text #5

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.6393. Min Act: -0.0000

Data Index: 822956 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.5886. Min Act: -0.0000

Data Index: 1346749 (The Pile)

Max Activating Token Index: 506

Text #7

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.5716. Min Act: -0.0000

Data Index: 197146 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.6787. Min Act: -0.0000

Data Index: 222299 (The Pile)

Max Activating Token Index: 45

Text #9

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.7562. Min Act: -0.0000

Data Index: 721489 (The Pile)

Max Activating Token Index: 832

Text #10

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.3451. Min Act: -0.0000

Data Index: 1627219 (The Pile)

Max Activating Token Index: 894

Text #11

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.5507. Min Act: -0.0000

Data Index: 1146877 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.7799. Min Act: -0.0000

Data Index: 1745184 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.5863. Min Act: -0.0000

Data Index: 456902 (The Pile)

Max Activating Token Index: 902

Text #14

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.3652. Min Act: -0.0000

Data Index: 184288 (The Pile)

Max Activating Token Index: 130

Text #15

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.3197. Min Act: -0.0000

Data Index: 1799163 (The Pile)

Max Activating Token Index: 218

Text #16

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.4003. Min Act: -0.0000

Data Index: 1803298 (The Pile)

Max Activating Token Index: 566

Text #17

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.4064. Min Act: -0.0000

Data Index: 1921393 (The Pile)

Max Activating Token Index: 520

Text #18

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.4117. Min Act: -0.0000

Data Index: 1009602 (The Pile)

Max Activating Token Index: 948

Text #19

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.5184. Min Act: -0.0000

Data Index: 1319972 (The Pile)

Max Activating Token Index: 524